Oscillator strength-driven machine learning for organic maximum absorption wavelength prediction

Z Zijian Lin (School of Nuclear Science and Technology) D Dechao Ye (Guangdong Provincial Key Laboratory of Optical Information Materials and Technology National Center for International Research on Green Optoelectronics, South China Academy of Advanced Optoelectronics, South China Normal University , Guangzhou 510006,) J Jianyu Luo (Guangdong Provincial Key Laboratory of Optical Information Materials and Technology National Center for International Research on Green Optoelectronics, South China Academy of Advanced Optoelectronics, South China Normal University , Guangzhou 510006,) Z Zhongshu Teng (Guangdong Provincial Key Laboratory of Optical Information Materials and Technology National Center for International Research on Green Optoelectronics, South China Academy of Advanced Optoelectronics, South China Normal University , Guangzhou 510006,) Y Yan Shen (Wuhan National Laboratory for Optoelectronics, School of Optical and Electronic Information, Huazhong University of Science and Technology, Luoyu Road 1037, Wuhan 430074 Hubei, People’s Republic of China) H Hailing Sun J Junpeng Fan (Guangdong Provincial Key Laboratory of Optical Information Materials and Technology National Center for International Research on Green Optoelectronics, South China Academy of Advanced Optoelectronics, South China Normal University , Guangzhou 510006,) G Guofu Zhou (National Center for International Research on Green Optoelectronics, Guangdong Provincial Key Laboratory of Optical Information Materials and Technology, Institute of Electronic Paper Displays, South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou 510006, China)

Abstract

Although organic chromogenic materials are critical for optoelectronic displays and imaging, accurate prediction of their maximum absorption wavelength (λmax) remains challenging: quantum chemical methods have long research and development cycles, and existing machine learning (ML) models lack physical constraints in limited-sample scenarios. Here, we propose an oscillator strength-driven ML framework (OS-ML), using excitation energy and transition dipole moment decomposed from oscillator strength as core physical descriptors. On a 74-molecule dataset, the optimal OS-ML-XGBoost model achieves a minimum prediction error of 0.6 nm, with an average deviation only 40% that of time-dependent density functional theory. This work provides an efficient approach for predicting the optical performance of organic optoelectronic materials in limited-sample scenarios.

Article Details

Volume / Issue Vol. 129, Issue 2
Published July 13, 2026
ISSN 0003-6951
Publisher American Institute of Physics

Journal Info

Applied Physics Letters

American Institute of Physics

ISSN: 0003-6951 Physical Sciences

Authors (8)

Z

Zijian Lin

School of Nuclear Science and Technology

D

Dechao Ye

Guangdong Provincial Key Laboratory of Optical Information Materials and Technology National Center for International Research on Green Optoelectronics, South China Academy of Advanced Optoelectronics, South China Normal University , Guangzhou 510006,

J

Jianyu Luo

Guangdong Provincial Key Laboratory of Optical Information Materials and Technology National Center for International Research on Green Optoelectronics, South China Academy of Advanced Optoelectronics, South China Normal University , Guangzhou 510006,

Z

Zhongshu Teng

Guangdong Provincial Key Laboratory of Optical Information Materials and Technology National Center for International Research on Green Optoelectronics, South China Academy of Advanced Optoelectronics, South China Normal University , Guangzhou 510006,

Y

Yan Shen

Wuhan National Laboratory for Optoelectronics, School of Optical and Electronic Information, Huazhong University of Science and Technology, Luoyu Road 1037, Wuhan 430074 Hubei, People’s Republic of China

H

Hailing Sun

J

Junpeng Fan

Guangdong Provincial Key Laboratory of Optical Information Materials and Technology National Center for International Research on Green Optoelectronics, South China Academy of Advanced Optoelectronics, South China Normal University , Guangzhou 510006,

G

Guofu Zhou

National Center for International Research on Green Optoelectronics, Guangdong Provincial Key Laboratory of Optical Information Materials and Technology, Institute of Electronic Paper Displays, South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou 510006, China